Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions and references to identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.61
     hen
    -0.45
    まい
    -0.44
     Lad
    -0.44
     terr
    -0.43
     Hald
    -0.42
     Ind
    -0.42
     ind
    -0.42
     vell
    -0.40
     lave
    -0.40
    POSITIVE LOGITS
     else
    0.75
     knows
    0.59
    IntoConstraints
    0.56
     demonios
    0.56
    Who
    0.56
    oping
    0.54
     parmi
    0.54
     cares
    0.54
     AMONG
    0.54
     betweenstory
    0.52
    Act Density 0.106%

    No Known Activations